eshansurendra/cell_anomaly_detection_using_autoencoders

This repository offers a TensorFlow-based anomaly detection system for cell images using adversarial autoencoders, capable of identifying anomalies even in contaminated datasets. Check out our code, pretrained models, and papers for more details.

20
/ 100
Experimental

This project helps medical technicians or researchers automatically identify abnormal cells in microscopy images. You provide a collection of cell images, and the system learns what 'normal' cells look like. It then flags any new images that deviate significantly from this learned normal pattern as potentially anomalous, even if your initial training data wasn't perfectly clean.

No commits in the last 6 months.

Use this if you need to reliably detect unusual cell images in a large dataset, especially when the definition of 'normal' might be subtly complex or your training data might contain a few outliers.

Not ideal if you need to classify cells into many different known categories or if you're working with data types other than images.

histopathology cytology microscopy medical-imaging quality-control
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/eshansurendra/cell_anomaly_detection_using_autoencoders"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.